Scholarlink

Acute Myeloid Leukemia (AML) is an aggressive form of blood cancer characterized by the rapid proliferation of immature white blood cells. Early detection is critical to improving survival rates, yet current diagnostic methods face limitations such as invasiveness, time consumption, and computational complexity. Recent advancements in quantum computing offer innovative approaches to enhance the diagnostic process. This manuscript explores the potential of quantum computing and quantum machine learning (QML) in the early detection and classification of AML. This work explores the use of hybrid quantum computing in conjunction with convolutional neural networks to perform computations for the diagnosis of AML cell images in situations where circuits utilizing a significant number of qubits are currently not feasible. There are two stages to the suggested hybrid QCNN architectures: phase 1 involves resizing AML cell images using quantum circuits, and phase 2 uses a CNN model to detect AML cell images. The proposed hybrid model achieved accuracy of 62.60% on the AML cell images dataset. The suggested hybrid QCNN model may enhance AML blood cancer diagnostic accuracy, based on these findings. This work highlights the potential of quantum machine learning for AML blood cancer patient detection. While current hardware constraints may limit the quantum advantage, advancements in quantum hardware are projected to improve future results.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Variational Quantum Circuit-Based Convolutional Neural Network Binary Image Classification Model to Detect Acute Myeloid Leukemia Blood Cancer

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Madhulata Kumari,
  • Kanad Ray,
  • Jesus Eduardo Lugo,
  • Jocelyn Faubert,
  • Khashayar Misaghian

摘要

Acute Myeloid Leukemia (AML) is an aggressive form of blood cancer characterized by the rapid proliferation of immature white blood cells. Early detection is critical to improving survival rates, yet current diagnostic methods face limitations such as invasiveness, time consumption, and computational complexity. Recent advancements in quantum computing offer innovative approaches to enhance the diagnostic process. This manuscript explores the potential of quantum computing and quantum machine learning (QML) in the early detection and classification of AML. This work explores the use of hybrid quantum computing in conjunction with convolutional neural networks to perform computations for the diagnosis of AML cell images in situations where circuits utilizing a significant number of qubits are currently not feasible. There are two stages to the suggested hybrid QCNN architectures: phase 1 involves resizing AML cell images using quantum circuits, and phase 2 uses a CNN model to detect AML cell images. The proposed hybrid model achieved accuracy of 62.60% on the AML cell images dataset. The suggested hybrid QCNN model may enhance AML blood cancer diagnostic accuracy, based on these findings. This work highlights the potential of quantum machine learning for AML blood cancer patient detection. While current hardware constraints may limit the quantum advantage, advancements in quantum hardware are projected to improve future results.